mlsanityData to 14 Oct 2026

Spacecraft Pose Estimation Based on Unsupervised Domain Adaptation and on a 3D-Guided Loss Combination

arXiv 2212.13415 ↗First posted 27 Dec 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Spacecraft pose estimation is a key task to enable space missions in which two spacecrafts must navigate around each other. Current state-of-the-art algorithms for pose estimation employ data-driven techniques. However, there is an absence of real training data for spacecraft imaged in space conditions due to the costs and difficulties associated with the space environment. This has motivated the introduction of 3D data simulators, solving the issue of data availability but introducing a large gap between the training (source) and test (target) domains. We explore a method that incorporates 3D structure into the spacecraft pose estimation pipeline to provide robustness to intensity domain shift and we present an algorithm for unsupervised domain adaptation with robust pseudo-labelling. Our solution has ranked second in the two categories of the 2021 Pose Estimation Challenge organised by the European Space Agency and the Stanford University, achieving the lowest average error over the two categories.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 27 of its 44 references that are in the map. First posted on arXiv 27 Dec 2022.

Builds on

27 of 44 references.

References · 27

  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  3. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  4. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  5. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  7. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  8. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 288
  9. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  10. 2017Integral Human Pose Regressioncited by 256
  11. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  12. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
15 more
  1. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  2. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  3. 2016Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptationcited by 163
  4. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  5. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  6. 2021Deep Regression on Manifolds: A 3D Rotation Case Studycited by 67
  7. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  8. 2021SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gapcited by 57
  9. 2019Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinementcited by 56
  10. 2019Deep Learning for Spacecraft Pose Estimation from Photorealistic Renderingcited by 54
  11. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  12. 2022Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gapcited by 44
  13. 2016Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimationcited by 34
  14. 2018Pose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networkscited by 34
  15. 2019Introduction to Camera Pose Estimation with Deep Learningcited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 3; 2026: 2.

12 papers.

  1. 20236D Object Pose Estimation from Approximate 3D Models for Orbital Roboticscited by 10
  2. 2024Bridging the Domain Gap for Flight-Ready Spaceborne Visioncited by 6
  3. 2024Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesiscited by 5
  4. 2025FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimationcited by 4
  5. 2024Domain Generalization for In-Orbit 6D Pose Estimationcited by 3
  6. 2024How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?cited by 3
  7. 2023SU-Net: Pose estimation network for non-cooperative spacecraft on-orbitcited by 2
  8. 2023LROC-PANGU-GAN: Closing the Simulation Gap in Learning Crater Segmentation with Planetary Simulatorscited by 0
  9. 2025A large-scale, physically-based synthetic dataset for satellite pose estimationcited by 0
  10. 2025Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimationcited by 0
  11. 2026CAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based Augmentationscited by 0
  12. 2026Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinementcited by 0